The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves and modifies data from project directories such as launch/, releases/, and gtm/, as well as files specified via @file references. This ingestion of untrusted local files creates a potential vector for indirect prompt injection. 1. Ingestion points: Searches and reads existing readiness assessments and project plans from the local filesystem. 2. Boundary markers: Absent; there are no specific instructions or delimiters to isolate data from potential instructions within the ingested files. 3. Capability inventory: The skill is limited to file system read and write operations for documentation management; it has no access to network tools or arbitrary command execution. 4. Sanitization: Absent; the skill does not implement validation or escaping for the content processed from external documents.
[NO_CODE]: The skill is entirely defined within the SKILL.md instructions and template; it does not contain any executable scripts, binaries, or external code dependencies.

launch-readiness